Page 99 - 2025年第56卷第5期

［ 24］ HUANG Q，SUN Y，XING Z，et al. Let's discover more API relations：A large language model-based AI chain for
.
/
unsupervised API relation inference［J/OL］ arXiv， 2023. （2023-11-02）［2025-01-05］ https：/arxiv.org/abs/
.

2311. 01266.
［ 25］ OUYANG L， WU J， JIANG X， et al. Training language models to follow instructions with human feedback［J］
.
Advances in Neural Information Processing Systems，2022，35：27730-27744.
［ 26］ ZHAO W X， ZHOU K， LI J， et al. A survey of large language models［J/OL］ arXiv， 2023. （2023-03-21）
.
［2025-01-05］ https：/arxiv. org/abs/2303. 18223.
/
.
［ 27］ AQRA I，ABDUL G，MAPLE C，et al. Incremental algorithm for association rule mining under dynamic threshold
.
［J］ Applied Sciences，2019，9（24）：5398.
［ 28］ HIKMAWATI E，MAULIDEVI N，SURENDRO K. Minimum threshold determination method based on dataset char⁃
acteristics in association rule mining［J］ Journal of Big Data，2021，8：1-17.
.
［ 29］ 刘峤，李杨，段宏，等 . 知识图谱构建技术综述［J］ 计算机研究与发展，2016，53（3）：582-600.
.
［ 30］ 许波刘，万皓，董增川，等 . 深圳市水利发展规划中智慧水利指标体系研究［J］ 人民长江，2024，55（2）：
.
252-258.
［ 31］ 邵 良 杉 ， 李 臣 浩 . 基 于 改 进 花 粉 算 法 的 极 限 学 习 机 分 类 模 型［J］ 计 算 机 工 程 与 应 用 ， 2020， 56（1）：
.
172-179.
Automated construction of schema and knowledge graphs for the operation and management
quality of hydraulic projects based on large language models

YANG Yangrui，DONG Fangning，WANG Pengfei，JIAN Pengpeng，LI Haikun

（School of Information Engineering，North China University of Water Resources and Electric Power，Zhengzhou 450000，China）

Abstract：At present，the quality management related data of hydraulic projects are mostly stored in unstructured

text with a low degree of digitization，making it difficult to meet the higher requirements for high-quality develop⁃
ment. To overcome the shortcomings of the current knowledge graph and knowledge graph schema construction meth⁃

ods，which rely heavily on manual labor and have poor efficiency. This paper proposes an Explore-Construct-Filter
（ECF）framework based on large language models （LLMs）to achieve automated construction of conceptual models

and knowledge graphs for the quality management of hydraulic project operation. The framework uses LLMs to first
discover the entities and relationship types of the knowledge graph，and then designs and generates a conceptual

model of the knowledge graph. Subsequently，under the guidance of the conceptual model，instances are extracted

from the data source to construct a knowledge graph. Finally，design a filtering mechanism to remove triplet noise
from conceptual models and knowledge graphs，ensuring accuracy. By setting the seed text set and the entire text set

data，the various components of the ECF framework are evaluated and compared with the existing methods. The
results show that the ECF framework performs well in the automatic construction of conceptual models and knowledge
graphs，with an accuracy rate 23% higher than that of existing methods，thus optimizing the efficiency of knowledge

graph construction，and providing technical and theoretical support for the standardized operation and steady prog⁃
ress of water conservancy engineering.

Keywords：Large Language Models；schema；knowledge graph；intelligent generation；operation and management

quality of hydraulic projects
（责任编辑：王 婧）

— 645 —